修改草稿

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must carry the full behavioral burden. It does disclose the most important trait — the article at index is replaced wholesale, so existing content at that position is overwritten — but it says nothing about whether other articles in the draft are untouched, what happens on an out-of-range index, or that image uploads (thumb_image/localize_images) are triggered as side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler; the core replace semantics and the index base are front-loaded, and the cross-reference follows. Nothing to trim.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with a 13-property nested object, no annotations and no output schema, the description covers the essential semantics and delegates field detail to the schema and to create draft. It is still thin on return behavior (whether an updated media_id comes back) and on failure modes such as index out of range, which an agent would want before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% and the nested article object already documents most fields, so this is near the baseline. The description adds two real pieces of meaning the schema does not: index is 0-based (repeated from the schema) and, more valuably, that the article object mirrors the single-article shape from wechat_create_draft, letting an agent reuse that mental model.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Uses a specific verb (整体替换 / wholesale replace) plus a precisely scoped resource (one article at position index in a draft). 'Entirely replace' implicitly distinguishes it from any partial-edit operation, and it points at wechat_create_draft as the parameter reference. It does not explicitly name which sibling to prefer over it, but the operation itself is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (modify an existing article in a draft) and gives a useful cross-reference that the article parameters match a single article in create draft. However, it never states prerequisites (the draft must already exist, media_id must be valid) or when to use this versus deleting and recreating a draft.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.